International Edu News: Customized courses make Singapore a suitable overseas Education Destination  |  National Edu News: Seminar on water by Richard N Zare at IISER Pune on Nov 25  |  Technology Inceptions: Apple Changing How It Develops Its Software After Buggy iOS 13 Debut  |  Teacher Insights: Unstable income in young age hits brain  |  Policy Indications: Research & Development and Training in Ayurveda & Traditional Medicine  |  Science Innovations: New system to control blood glucose levels  |  International Edu News: Foreign-run schools under scrutiny in China  |  Management lessons: UNIGE to Launch Business Center to Sensitize Industry on Human Rights  |  Technology Inceptions: Harman Kardon Citation Series home speakers launched  |  Teacher Insights: Parental roles improve life satisfaction  |  Parent Interventions: Distinct types of teen popularity identified  |  Policy Indications: Hybrid Annuity Model for National Highways  |  Policy Indications: IFFI@50 will inform, educate and attract Youth and Children   |  Leadership Instincts: Need to Create Safe Homes and Safe Neighborhoods  |  Health Monitor: Ayurveda Medicines for Treating Lifestyle Diseases  |  
August 21, 2017 Monday 09:36:29 PM IST

Speech recognition by MS a new milestone

Technology Inceptions

San Francisco: Microsofts conversational speech recognition system -- designed to accurately recognises the words in a conversation like humans do -- has reached a 5.1 per cent error rate, its lowest so far.

This milestone means that, for the first time, a computer can recognise the words in a conversation as well as a person would.

"Our research team reached that 5.1 per cent error rate with our speech recognition system, a new industry milestone, substantially surpassing the accuracy we achieved last year," Microsoft said in a blog post late on Sunday.

Last year in October, the team from Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists. The researchers had then reported a word error rate (WER) of 5.9 percent.


"Last year, Microsoft's speech and dialog research group announced a milestone in reaching human parity on the 'Switchboard' conversational speech recognition task, meaning we had created technology that recognised words in a conversation as well as professional human transcribers," said Xuedong Huang, Technical Fellow, Microsoft.

'Switchboard' is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to benchmark speech recognition systems. 

The task involves transcribing conversations between strangers discussing topics such as sports and politics. The team used "Microsoft Cognitive Toolkit 2.1" (CNTK), the most scalable deep learning software available, for exploring model architectures. 

Additionally, Microsoft's investment in cloud compute infrastructure, specifically Azure GPUs, helped improve the effectiveness and speed.


Reaching human parity with an accuracy on par with humans has been a research goal for the last 25 years. 

"Microsoft's willingness to invest in long-term research is now paying dividends for our customers in products and services such as Cortana, Presentation Translator, and Microsoft Cognitive Services," the post read. "Moving from recognising to understanding speech is the next major frontier for speech technology," the post added.

Comments